© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 22-GEMMASCOPE-RES-16K
    11. 13719
    Prev
    Next
    INDEX
    Explanations

    negations or qualifiers that suggest uncertainty or denial

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Sentences starting with "Not"

    np_acts-logits-general · gemini-2.0-flash

    not followed by sure, only, necessarily

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     EconPapers
    -0.44
     asemenea
    -0.42
    Base
    -0.41
     asimismo
    -0.40
    xtext
    -0.40
    |<\
    -0.39
    ChromeDriver
    -0.39
    penup
    -0.39
     (~
    -0.39
    bute
    -0.39
    POSITIVE LOGITS
     sure
    1.20
    withstanding
    1.14
    WebVitals
    0.93
     initComponents
    0.87
     gonna
    0.82
     everyone
    0.81
     MainAxisSize
    0.80
     SURE
    0.77
    Sure
    0.77
     many
    0.76
    Activations Density 0.098%

    No Known Activations